From e637348f05049a6f6275974e1ecfbc3f71d3bc88 Mon Sep 17 00:00:00 2001
From: Kumar Saurabh <kumarsaurabh772@gmail.com>
Date: Mon, 18 Mar 2019 23:24:15 +0530
Subject: [PATCH] Pulling JSON from url

Following things are implemented-
1. Pulled JSON from url : https://envirocar.org/api/stable/tracks/52714d4ee4b000fe0582a292/measurements
2. Discarded unnecessary data
3. Adding custom Headers and created dataframe.
4. Done Data description
Now it is ready for further statistical work.
---
 notebooks/enviroCar_python.ipynb | 197 +++++++++++++++++++++++++++++++
 1 file changed, 197 insertions(+)
 create mode 100644 notebooks/enviroCar_python.ipynb

diff --git a/notebooks/enviroCar_python.ipynb b/notebooks/enviroCar_python.ipynb
new file mode 100644
index 0000000..4076454
--- /dev/null
+++ b/notebooks/enviroCar_python.ipynb
@@ -0,0 +1,197 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from pandas.io.json import json_normalize\n",
+    "import json\n",
+    "import urllib.request, json "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with urllib.request.urlopen(\"https://envirocar.org/api/stable/tracks/52714d4ee4b000fe0582a292/measurements\") as url:\n",
+    "    data_json = json.loads(url.read().decode())\n",
+    "    #print(data)\n",
+    "data=data_json['features']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Preparing column list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "good_columns = [\n",
+    "     \"Coordinates\",\n",
+    "     \"Geometry Type\",\n",
+    "     \"ID\",\n",
+    "     \"CO2(kg/h)\",\n",
+    "     \"Calculated MAF\",\n",
+    "     \"Consumption\",\n",
+    "     \"GPS Accuracy\",\n",
+    "     \"GPS Altitude\",\n",
+    "     \"GPS Bearing\",\n",
+    "     \"GPS HDOP\",\n",
+    "     \"GPS PDOP\",\n",
+    "     \"GPS Speed\",\n",
+    "     \"GPS VDOP\",\n",
+    "     \"Intake Pressure\",\n",
+    "     \"Intake Temperature\",\n",
+    "     \"Rpm\",\n",
+    "     \"Speed\",\n",
+    "     \"Construction_Year\",\n",
+    "     \"EngineDisplacement\",\n",
+    "     \"FuelType\",\n",
+    "     \"Sensor ID\",\n",
+    "     \"Manufacturer\",\n",
+    "     \"Model\",\n",
+    "     \"Sensor type'\",\n",
+    "     \"Time\",\n",
+    "     \"Track\",\n",
+    "     \"Type\"\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Preparing Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_1 = pd.DataFrame.from_dict(json_normalize(data), orient='columns')\n",
+    "\n",
+    "#Filtering columns\n",
+    "df=df_1.filter(regex='^(?!.*unit).*$', axis=1)\n",
+    "\n",
+    "#Attaching custom columns\n",
+    "df.columns = good_columns\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert dates to datetime\n",
+    "df['Time'] = pd.to_datetime(df.Time,format = '%Y-%m-%dT%H:%M:%SZ')\n",
+    "\n",
+    "#Setting Time column as Index\n",
+    "df.set_index('Time', drop=True)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Extracting Longitude and Latitude from Coordinates\n",
+    "a['Coordinates'].tolist()\n",
+    "length=len(a['Coordinates'])\n",
+    "longitude = list()\n",
+    "latitude= list()\n",
+    "for ele in range(10):\n",
+    "    #parts=ele.split(\",\")\n",
+    "    #longitude=parts[1]\n",
+    "    #latitude =parts[2] \n",
+    "    #print(parts[0])\n",
+    "    print(['Coordinates'][ele][0])\n",
+    "    #latitude= (a['Coordinates'][i][1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Show variable types\n",
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Descriptive statistics"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}